The Visual Target Matters: Learning across the Visual Hierarchy for Brain-to-Image Retrieval
本文提出NeuroGlyph方法,通过学习视觉层次中不同深度的信息来优化脑-图像检索目标,超越了仅使用最终层的方法。
本文提出NeuroGlyph方法,通过学习视觉层次中不同深度的信息来优化脑-图像检索目标,超越了仅使用最终层的方法。
研究通过检测笑声来索引日常生活中的积极时刻,利用LaughAnchor系统帮助用户记录、回顾和反思这些时刻,从而支持正面经历的重构与反思。
本文提出VESTA,一种无训练的长视频代理,通过策略引导的多策略检索解决证据获取问题,提高视频理解准确性。
This work addresses the challenge of constructing a persistent, autonomously updatable, and geometrically verifiable world model for long-term service robots operating in unknown environments—a task hindered by error accumulation, static scene representations, and insufficient 3D geometric evidence in existing approaches. The authors propose a baseline-increment decoupled active graph framework that separates stable static structures from revisable dynamic objects, building a structural baseline through autonomous exploration and performing uncertainty-aware verification via hierarchical object beliefs. A novel reliability-weighted state representation and a geometry-aware visibility gating mechanism are introduced to jointly inform graph-conditioned viewpoint planning, effectively mitigating erroneous deletions under occlusion and enhancing object identity continuity and event recall. Experiments demonstrate significant improvements over baselines in multi-environment simulations, with superior performance in static-object F1 scores, identity continuity, and event recall, and successful integration with onboard systems is validated on a physical robot.
This work addresses the poor physical feasibility and inefficient high-dimensional optimization inherent in black-box physical adversarial attacks for remote sensing object detection by proposing ColorFD, a novel method that employs solid-color patches as physical perturbations. ColorFD jointly optimizes patch location and color via differential evolution, significantly reducing the search space through an innovative integration of finite-difference-guided critical region localization and class-level spatial priors. Furthermore, it introduces a target-aware fitness mechanism to enhance both attack specificity and transferability. Experimental results demonstrate that ColorFD consistently outperforms existing black-box approaches across YOLOv3u, YOLOv5u, and Faster R-CNN detectors, achieving performance close to white-box baselines, with digital-domain optimizations effectively transferring to real-world imaging conditions.
本文提出NeuroGlyph方法,通过学习视觉层次中不同深度的信息来优化脑-图像检索目标,超越了仅使用最终层的方法。
研究通过检测笑声来索引日常生活中的积极时刻,利用LaughAnchor系统帮助用户记录、回顾和反思这些时刻,从而支持正面经历的重构与反思。
本文提出VESTA,一种无训练的长视频代理,通过策略引导的多策略检索解决证据获取问题,提高视频理解准确性。
This work addresses the challenge of constructing a persistent, autonomously updatable, and geometrically verifiable world model for long-term service robots operating in unknown environments—a task hindered by error accumulation, static scene representations, and insufficient 3D geometric evidence in existing approaches. The authors propose a baseline-increment decoupled active graph framework that separates stable static structures from revisable dynamic objects, building a structural baseline through autonomous exploration and performing uncertainty-aware verification via hierarchical object beliefs. A novel reliability-weighted state representation and a geometry-aware visibility gating mechanism are introduced to jointly inform graph-conditioned viewpoint planning, effectively mitigating erroneous deletions under occlusion and enhancing object identity continuity and event recall. Experiments demonstrate significant improvements over baselines in multi-environment simulations, with superior performance in static-object F1 scores, identity continuity, and event recall, and successful integration with onboard systems is validated on a physical robot.
This work addresses the poor physical feasibility and inefficient high-dimensional optimization inherent in black-box physical adversarial attacks for remote sensing object detection by proposing ColorFD, a novel method that employs solid-color patches as physical perturbations. ColorFD jointly optimizes patch location and color via differential evolution, significantly reducing the search space through an innovative integration of finite-difference-guided critical region localization and class-level spatial priors. Furthermore, it introduces a target-aware fitness mechanism to enhance both attack specificity and transferability. Experimental results demonstrate that ColorFD consistently outperforms existing black-box approaches across YOLOv3u, YOLOv5u, and Faster R-CNN detectors, achieving performance close to white-box baselines, with digital-domain optimizations effectively transferring to real-world imaging conditions.